Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4432 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.5868. Min Act: -0.0001

Data Index: 160155 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4214. Min Act: -0.0001

Data Index: 63153 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3983. Min Act: -0.0001

Data Index: 1056347 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2771. Min Act: -0.0001

Data Index: 584439 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2822. Min Act: -0.0001

Data Index: 503080 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2417. Min Act: -0.0001

Data Index: 147253 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3603. Min Act: -0.0001

Data Index: 45820 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3893. Min Act: -0.0001

Data Index: 400310 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3172. Min Act: -0.0001

Data Index: 1340694 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2493. Min Act: -0.0001

Data Index: 1272139 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.3066. Min Act: -0.0001

Data Index: 800710 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.4169. Min Act: -0.0001

Data Index: 631503 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2313. Min Act: -0.0001

Data Index: 48877 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2122. Min Act: -0.0001

Data Index: 745398 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2056. Min Act: -0.0001

Data Index: 682951 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2015. Min Act: -0.0001

Data Index: 953769 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2645. Min Act: -0.0001

Data Index: 1057041 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2274. Min Act: -0.0001

Data Index: 503029 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.1836. Min Act: -0.0001

Data Index: 1185382 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.5868. Min Range: -1.5868

Max Act: 1.2581. Min Act: -0.0001

Data Index: 995783 (C4 (Web Text))

Max Activating Token Index: 189